© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9610
    Prev
    Next
    INDEX
    Explanations

    indicator variables and series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berkel
    0.46
     userName
    0.45
     continuamente
    0.42
    肉
    0.42
     LastName
    0.41
    两人
    0.40
     vele
    0.40
     snel
    0.39
    পরে
    0.39
     passwd
    0.39
    POSITIVE LOGITS
    シャ
    0.43
    Swiss
    0.43
    Fra
    0.41
    ém
    0.40
    ζ
    0.40
    Pro
    0.39
     Fra
    0.39
     Applied
    0.39
    applic
    0.39
    zeta
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.